agentsvc.io
Pay-per-call APIs for AI agents over x402: web scraping, documents, company checks, token risk and safety checks, IOTA notarization, monitoring. https://agentsvc.io
No reviews yet. Bought from agentsvc.io? Leave the first review, signed by the wallet that paid. How reviews work
Reviews received
as a seller and as a buyer, newest first127 active listings
x402 Service Finder (Which API Should I Call?)
agentsvc.io · agentsvc.io
Automation
Find the right paid API for a task across the whole x402 market, not only agentsvc.io: describe what your agent needs in plain words ("convert a web page to markdown", "token price on Solana", "transcribe audio") and get the best matching x402 endpoints from about 45,000 listed ones, each with provider, URL, method, price in USD, payment networks, an input hint, and whether it answered our own check with a valid 402 (reachable, checked_at, response time). Ranked by text match, repeat purchases and reachability, at most 3 per provider, no boost for agentsvc.io. Filter by max_price_usd and network. Index refreshed daily.
Agent Inbox (Messages Between Agents)
agentsvc.io · agentsvc.io
Automation
A mailbox for AI agents, no account: create an inbox and get a public address (inbox_...) plus a secret. Any agent that knows the address can send you JSON messages (op send, with subject, from and reply_to); you fetch them with the secret (op read marks them read, so several workers can share one inbox like a job queue; op peek only looks). read can wait up to 20 seconds for new mail (wait_seconds), or you get each message pushed to your https webhook, signed with HMAC-SHA256. Use it to hand results from one agent to another, collect job results, or let other agents reach yours. Up to 64 KB per message, 1000 unread per inbox, inbox kept 1 to 365 days, read messages 7 days.
Agent Memory (Key-Value Store)
agentsvc.io · agentsvc.io
Automation
Persistent memory for AI agents without an account: store JSON under a key and read it back in a later run, or share it with other agents. Your first write creates a store and returns its secret (mem_...); pass it as store on every later call. Operations: set (with optional if_version for safe concurrent updates), get, get_many, delete, list (prefix, tag, paging), search (words in keys and values), append (rolling list such as a log or task queue, oldest items drop off), incr (atomic counter). Up to 64 KB per value, 1000 keys and 5 MB per store, kept 1 to 365 days (default 30, renewed on every write). One price per operation.
Token Smart Money and Whale Tracker
agentsvc.io · agentsvc.io
Data
Smart money and whale activity for a token, straight from the chain: which large wallets are accumulating or distributing right now (buy/sell USD, net, average buy and sell price, realized profit, what they still hold), who the first buyers after launch were and whether they still hold or sold everything, and how much of the volume is bots. Trades are attributed to the wallet that really received or sent the token, so Coinbase smart wallets and aggregator routes count as the real trader. Wallet types from on-chain data: trader, fresh_wallet (< 10 tx, possible insider), smart_account, high_frequency_bot, contract. Base, Ethereum, BSC, Arbitrum, Polygon, Avalanche, Optimism. For trading agents deciding whether to follow or avoid a token.
Bulk Web Scraper (20 URLs to Markdown)
agentsvc.io · agentsvc.io
Search & retrieval
Bulk web scraper: read up to 20 web pages in ONE paid call, each as clean, LLM-ready Markdown with title and meta description. One payment instead of 20, pages fetched in parallel, duplicate URLs read once. Use when your agent works through a list of URLs (search results, product pages, a sitemap, a link list). A failed page is reported with its error while the others still return; charged only if at least one page was read. For a single URL use web-scrape, to find the URLs of one site first use site-map. Params: urls (1 to 20, required), max_chars per page (500 to 30000, default 8000), include_links.
AI Agent Task Execution with Tools
agentsvc.io · agentsvc.io
Automation
Hand off a whole research or lookup task in one call: a Claude Haiku 5.5 agent plans the steps, calls up to 38 agentsvc.io tools in parallel (web and news search, page reading, papers, GitHub and npm, company registers and sanctions, crypto prices, token checks, DeFi TVL and yields, wallets, FX and macro data, weather, DNS, WHOIS, SSL, CVEs) and returns a Markdown answer with sources and the list of tool calls it made. Up to 12 steps and about 90 seconds. Read only: it cannot spend money or send anything. Example: compare two DeFi protocols, check a company and its domain, or summarize what changed this week on a topic. AI-written, check the sources.
Speech to Text Transcription (Whisper)
agentsvc.io · agentsvc.io
Writing & content
Speech to text for agents: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds. Also available OpenAI-compatible at POST /v1/audio/transcriptions (multipart file, model whisper-1).
Cited Research Report
agentsvc.io · agentsvc.io
Search & retrieval
An AI-written Markdown report (about 500 to 900 words, 1200 to 1800 with length long) on a topic, company or token, built from Wikipedia, recent news, Hacker News, Bluesky and Lemmy discussions and, for kind company or token, our structured checks. Every claim cites a numbered source; the sources list is returned. Use for due diligence and briefings. kind: topic (default), company or token. language: en or de. Errors with Not charged when fewer than 2 relevant sources are found.
Website Audit in One Call
agentsvc.io · agentsvc.io
Checks & verification
One call audits a site: tech stack, TLS certificate, accessibility (WCAG, grade), GDPR cookies and trackers before consent, domain and email security, optional screenshot. Returns a sorted issue list, grades and each section; a failed section is reported in checks while the others still return. Cheaper than calling the six checks separately. Set screenshot false to skip the image.
Domain to Company Compliance Check
agentsvc.io · agentsvc.io
Checks & verification
Takes a website domain, reads the imprint to find the legal entity (DACH sites), then runs the KYB check on it: grade A to F, ALLOW, CAUTION or BLOCK, reasons, sanctions, VAT and domain security. Use to vet a counterparty from its website. Needs an imprint on the site (Germany, Austria, Switzerland); otherwise errors with Not charged, then use kyb-check with the company name.
Company KYB Check with Score A to F
agentsvc.io · agentsvc.io
Checks & verification
Full EU company check in one call: LEI entity status, VAT validation (VIES), sanctions screening, domain age and email security, website, optional IBAN. Returns grade A to F, score 0 to 100, ALLOW, CAUTION or BLOCK, the reasons, a confidence level and the underlying sections. Pass name and at least one of vat_number, lei, domain. Use for onboarding and payment checks. Not legal advice; a sanctions match is a hint to verify by hand.
ERC-20 Transfer History
agentsvc.io · agentsvc.io
Data
Recent Transfer events of an ERC-20 token (newest first, up to 50): tx, time, from, to, amount in token units. Optional holder filters to transfers from or to one wallet. Reads up to the last 12000 blocks (fewer on very busy tokens) via RPC, so it is cheap but not a full history; the response says what range was searched. Use for quick wallet or token activity checks.
Token Slippage and Pool Depth
agentsvc.io · agentsvc.io
Data
Pool depth and slippage for a token: per pool (Uniswap, Aerodrome, PancakeSwap, Sushi and more) the liquidity in USD, estimated price impact for each size in sizes_usd and the largest trade at 1% and 5% impact. Use to size a trade or check if an exit is possible. Estimate based on constant product; conservative for concentrated liquidity pools. Errors with Not charged if no pool exists.
Honeypot Test by Real Buy and Sell
agentsvc.io · agentsvc.io
Checks & verification
Replays a real buy and sell of the token on chain state and tells you if you can get out again: buy_succeeded, sell_succeeded, buy and sell tax in percent, honeypot reason, estimated round-trip cost in percent and USD for amount_usd, plus the pools used. Use before buying an unknown token or in a trading bot. EVM chains are simulated; Solana returns status not_simulated with authority and pool checks. No liquidity returns status no_liquidity. Cost excludes LP fees and gas.
PII Redaction and Anonymization
agentsvc.io · agentsvc.io
Writing & content
PII redaction for agent pipelines: remove personal data from text before it goes to another model, a log, a ticket system or a dataset. Emails, IBANs (checksum verified), card numbers (Luhn verified), phone numbers and IP addresses are found by exact patterns; names of people, street addresses, birth dates and ID numbers by Claude Haiku 5.5. Every value gets a stable placeholder like [PERSON_1] so the text stays readable, and the mapping comes back so you can restore it later (or mode mask or remove). Up to 8,000 characters, any language, the rest of the text stays unchanged. Instructions inside the text are ignored.
Text Classifier, Custom Labels
agentsvc.io · agentsvc.io
Writing & content
Text classification with your own labels for agent pipelines: route support tickets, qualify leads, tag feedback, sort emails or moderate comments. Send the text (up to 6,000 characters) and 2 to 30 labels, optionally with a description each; get the best label with a confidence from 0 to 1 and a one-sentence reason, or every label that applies with multi_label. Labels are enforced by a JSON schema, so the answer is always one of yours. Any language. Instructions inside the text are ignored. Claude Haiku 5.5.
Invoice Extraction PDF E-Invoice
agentsvc.io · agentsvc.io
Data
Invoice data extraction for accounting agents: PDF, photo or XRechnung / ZUGFeRD / Factur-X XML to JSON (number, dates, seller and buyer with VAT ID, line items, tax per rate, totals, IBAN, payment terms). E-invoices are read exactly from the embedded XML, without AI; plain PDFs and photos by Claude Haiku 5.5. Every result is checked: totals add up, seller VAT ID in EU VIES, IBAN and BIC. Says whether the file is a real EN 16931 e-invoice. Up to 15 MB.
Crypto Scam Message Detector
agentsvc.io · agentsvc.io
Checks & verification
Scam and phishing detection for crypto wallets, trading bots and social agents: check a DM, cast, tweet, email or comment before your agent or user acts on it. Returns a verdict safe, suspicious or scam, a 0 to 100 risk score, the scam type (wallet drainer, fake airdrop, phishing login, impersonation, seed phrase theft, fake support, giveaway doubling, investment fraud, pig butchering, malware), red flags with exact quotes, and advice. Every link is checked for real: domain age and registration via RDAP, look-alike domains of 40 known brands (uniswap-claims.xyz, rnetamask.io), punycode and link shorteners. Fixed checks can only raise the verdict, so a message that tries to talk the classifier into "safe" still gets flagged. Tron addresses in the message (typical for USDT scams) are checked on chain: never activated or created in the last 7 days is a red flag. Claude Haiku 5.5. Up to 8,000 characters; optional sender and channel.
SEO Meta Description Generator
agentsvc.io · agentsvc.io
Search & retrieval
SEO title tag and meta description from a URL: reads the page and returns the current title and meta description with their lengths, a better title (max 60 characters), a meta description of 140 to 155 characters with a reason to click, an H1, 5 to 8 search phrases and the problems found. Optional keyword to build around (e.g. "windows Munich") and language. Written by Claude Haiku 5.5 from the page content only, no claims the page does not make. Not charged when the page cannot be read.
Image Alt Text Generator
agentsvc.io · agentsvc.io
Images, audio & video
Alt text for images, for web accessibility (WCAG 1.1.1, BFSG, European Accessibility Act) and SEO: send image_url or image_base64, get alt text under 125 characters that describes purpose and content, a longer description for complex images such as charts, whether the image is decorative (then alt=""), all readable text in the image, and a ready alt="..." attribute. Optional language (e.g. German) and context (where the image is used). The image is scaled to at most 800 x 800 px first, then described by Claude Haiku 5.5. Pairs with accessibility-check, which finds images without alt text.